Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    programming or technical terms related to definitions and versions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tagHelper
    -0.59
     Ejecutivo
    -0.56
     denounce
    -0.53
    houd
    -0.50
    organisme
    -0.49
     setae
    -0.49
     furthest
    -0.48
    hålla
    -0.48
    fillType
    -0.48
     beſt
    -0.47
    POSITIVE LOGITS
    Pl
    0.69
     pleading
    0.67
     Pl
    0.67
    Melt
    0.67
    ple
    0.64
     Melt
    0.64
     PL
    0.63
     pl
    0.62
    האם
    0.61
     Plu
    0.61
    Act Density 2.137%

    No Known Activations